Hello, In the exercise guide it says : " It’s important to note that the "y_pred " and "y_true " inputs of tf.keras.losses.categorical_crossentropy are expected to be of shape (number of examples, num_classes) " We already have both logits and labels as the same shape (6, 2) = (num of classes, num…

Week 3 Exercise 6 - compute_total_loss. Why transpose?

Course Q&A Deep Learning Specialization Improving Deep Neural Networks: Hyperparameter tun

paulinpaloalto November 21, 2023, 4:17pm 4

Glad to hear that you figured out the from_logits issue. Here’s a thread that explains why it is done with the “True” setting in the assignment and “going forward” in the rest of the courses.

1 Like

Topic		Replies	Views
Week 3 - Exercise 6 - Compute Total Loss Improving Deep Neural Networks: Hyperparameter tun	8	1324	April 3, 2024
Wk 3, Prog. exercise 6: do I have to reshape the "logits" and "labels"? Improving Deep Neural Networks: Hyperparameter tun	7	555	October 11, 2022
ERROR: Did you get the reduce sum of your loss functions? Improving Deep Neural Networks: Hyperparameter tun week-3	1	32	September 25, 2024
DLS course2 week 3 exercise 6(compute total loss) Improving Deep Neural Networks: Hyperparameter tun	1	529	February 8, 2023
Course 2 Week 3 assignment, Ex6 Improving Deep Neural Networks: Hyperparameter tun	2	429	June 28, 2023

Week 3 Exercise 6 - compute_total_loss. Why transpose?

Related topics